Model compression and hardware acceleration for neural networks: A comprehensive survey

L Deng, G Li, S Han, L Shi, Y ** of input-output channels
J Zhu, J Pei - Neurocomputing, 2022 - Elsevier
As the smallest structural unit of feature map**, the convolution kernel in a deep
convolution neural networks (DCNN) convolutional layer is responsible for the input channel …

Stealthy backdoors as compression artifacts

Y Tian, F Suya, F Xu, D Evans - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Model compression is a widely-used approach for reducing the size of deep learning
models without much accuracy loss, enabling resource-hungry models to be compressed for …

Pcnn: Pattern-based fine-grained regular pruning towards optimizing cnn accelerators

Z Tan, J Song, X Ma, SH Tan, H Chen… - 2020 57th ACM/IEEE …, 2020 - ieeexplore.ieee.org
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a
fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask …